Triple

T13872059
Position Surface form Disambiguated ID Type / Status
Subject Kaduna Refining and Petrochemical Company E333477 entity
Predicate regulator P46 FINISHED
Object NMDPRA
NMDPRA is Nigeria’s downstream petroleum regulatory authority responsible for overseeing and enforcing standards in the country’s midstream and downstream oil and gas sector.
 E1065451 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: NMDPRA | Statement: [Kaduna Refining and Petrochemical Company, regulator, NMDPRA]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: NMDPRA
Context triple: [Kaduna Refining and Petrochemical Company, regulator, NMDPRA]
  • A. NDMC
    NDMC is the civic administrative body responsible for municipal services and infrastructure in New Delhi’s central and VIP areas.
  • B. NMP
    NMP is the three-letter National Rail station code assigned to Northampton railway station in Northampton, England.
  • C. DNMA
    DNMA is the ICAO airport code for Maiduguri International Airport in Maiduguri, Nigeria.
  • D. NHPA
    NHPA is a landmark U.S. federal law that established the framework for preserving historic buildings, sites, and cultural resources nationwide.
  • E. NDPG
    NDPG is an abbreviation for Japan’s National Defense Program Guidelines, a key policy document outlining the country’s medium- to long-term defense strategy and force structure.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: NMDPRA
Triple: [Kaduna Refining and Petrochemical Company, regulator, NMDPRA]
Generated description
NMDPRA is Nigeria’s downstream petroleum regulatory authority responsible for overseeing and enforcing standards in the country’s midstream and downstream oil and gas sector.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: NMDPRA
Target entity description: NMDPRA is Nigeria’s downstream petroleum regulatory authority responsible for overseeing and enforcing standards in the country’s midstream and downstream oil and gas sector.
  • A. NDMC
    NDMC is the civic administrative body responsible for municipal services and infrastructure in New Delhi’s central and VIP areas.
  • B. NMP
    NMP is the three-letter National Rail station code assigned to Northampton railway station in Northampton, England.
  • C. DNMA
    DNMA is the ICAO airport code for Maiduguri International Airport in Maiduguri, Nigeria.
  • D. NHPA
    NHPA is a landmark U.S. federal law that established the framework for preserving historic buildings, sites, and cultural resources nationwide.
  • E. NDPG
    NDPG is an abbreviation for Japan’s National Defense Program Guidelines, a key policy document outlining the country’s medium- to long-term defense strategy and force structure.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d81c5ced9c8190b0e9bcc6effe5959 completed April 9, 2026, 9:38 p.m.
NER Named-entity recognition batch_69de05c638248190bbe5d19f7b88d0f9 completed April 14, 2026, 9:15 a.m.
NED1 Entity disambiguation (via context triple) batch_69f7c107c20c81909dff0ca4a59fcc55 completed May 3, 2026, 9:41 p.m.
NEDg Description generation batch_69f7c20da9448190b3167b091bd39b94 completed May 3, 2026, 9:45 p.m.
NED2 Entity disambiguation (via description) batch_69f7c2cc63148190b9ca2828abe54286 completed May 3, 2026, 9:49 p.m.
Created at: April 9, 2026, 10:14 p.m.